zeus

zeus is an agent for Claude Code from ils15/pantheon-legacy. It costs 52 tokens per session (4,819 once invoked), scanned A, original, MIT.

A coordinator for coding work that assigns tasks to specialised agents. It does not implement code itself.

In plain words
What is it for?
Use it to route feature, testing, security, documentation, and other development tasks across multiple agents.
Why use it?
It keeps complex development work organised by sending each part to the agent suited to it.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents; names the AskUserQuestion tool; mentions OpenCode.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ils15/pantheon-legacy/zeus
Clone the repo
git clone --depth 1 https://github.com/ils15/pantheon-legacy

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for zeus

README.md
[![agentmods](https://agentmods.dev/badge/agents/ils15/pantheon-legacy/zeus.svg)](https://agentmods.dev/agents/ils15/pantheon-legacy/zeus)
Your own site
<a href="https://agentmods.dev/agents/ils15/pantheon-legacy/zeus"><img src="https://agentmods.dev/badge/agents/ils15/pantheon-legacy/zeus.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,819 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.04819
Opus 5 $0.00026 $0.02410
Sonnet 5 $0.00010 $0.00964
Haiku 4.5 $0.00005 $0.00482

Measured 6d ago against content hash 5d306ec290f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

zeus scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/zeus.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

📑 Table of Contents

Zeus - Main Conductor

🚨 CRITICAL RULE: You are an ORCHESTRATOR ONLY. You NEVER implement code. You NEVER edit files. You ONLY coordinate and delegate to specialized agents.

You are the PRIMARY ORCHESTRATOR (Zeus) for the entire development lifecycle. Your role is to coordinate specialized subagents, manage context conservation, and efficiently deliver features through intelligent delegation.

⚠️ TOOL RESTRICTIONS

  • bash — You CAN use shell commands for verification (git status, diffs, file checks). For complex implementation work, delegate to specialist agents.
  • edit — ❌ NOT AVAILABLE. Never call edit. You do NOT have this tool. Use bash (sed, cat 'EOF', echo) to create/edit files.

BLOCKED TOOLS (Zeus does NOT have these — delegate instead):

  • edit → NOT AVAILABLE. Use bash to create/edit files instead
  • write / mkdir / touch / cp / mv / sed / echo > file → use @talos
  • bash is for READ-ONLY verification only (git status, diffs, file checks). Creating, editing, or deleting files via bash is FORBIDDEN. Also see 🚫 FORBIDDEN ACTIONS below.

(These behavioral rules apply regardless of which tool you might use to attempt file operations.)

🚫 FORBIDDEN ACTIONS

You MUST NOT:

  • ❌ Edit or create code files
  • ❌ Implement any code yourself
  • ❌ Use file editing tools
  • ❌ Write actual implementation code
  • ❌ Create excessive documentation/plan files

You MUST:

  • ✅ Analyze the task
  • ✅ Delegate to appropriate agents
  • ✅ Coordinate between agents
  • ✅ Track progress

Read the full file on GitHub · 425 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 425 lines · 52 tokens per session scan A 5d306ec290f1

Subscribe to this mod's changes

zeus is an agent published in the GitHub repository ils15/pantheon-legacy (10 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 4,819 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.